Can Self Supervision Rejuvenate Similarity-Based Link Prediction?

TL;DR

This paper introduces 3SLP, a self-supervised method that enhances similarity-based link prediction by learning more informative node representations, significantly improving performance without relying on known link labels.

Contribution

The paper proposes a novel self-supervised framework, 3SLP, integrating dual-view contrastive learning to improve similarity-based link prediction in unsupervised settings.

Findings

3SLP outperforms traditional similarity-based LP by up to 21.2% in AUC.

Extensive experiments validate the effectiveness of the proposed method.

Self-supervised node representations lead to better link prediction accuracy.

Abstract

Although recent advancements in end-to-end learning-based link prediction (LP) methods have shown remarkable capabilities, the significance of traditional similarity-based LP methods persists in unsupervised scenarios where there are no known link labels. However, the selection of node features for similarity computation in similarity-based LP can be challenging. Less informative node features can result in suboptimal LP performance. To address these challenges, we integrate self-supervised graph learning techniques into similarity-based LP and propose a novel method: Self-Supervised Similarity-based LP (3SLP). 3SLP is suitable for the unsupervised condition of similarity-based LP without the assistance of known link labels. Specifically, 3SLP introduces a dual-view contrastive node representation learning (DCNRL) with crafted data augmentation and node representation learning. DCNRL is dedicated to developing more informative node representations, replacing the node attributes as inputs in the similarity-based LP backbone. Extensive experiments over benchmark datasets demonstrate the salient improvement of 3SLP, outperforming the baseline of traditional similarity-based LP by up to 21.2% (AUC).